Angular triangle distance for ordinal metric learning
- URL: http://arxiv.org/abs/2211.15200v1
- Date: Mon, 28 Nov 2022 10:18:06 GMT
- Title: Angular triangle distance for ordinal metric learning
- Authors: Imam Mustafa Kamal and Hyerim Bae
- Abstract summary: This study proposes a novel angular triangle distance (ATD) and ordinal triplet network (OTD) to obtain an accurate embedding space representation for ordinal data.
We show that our proposed method not only semantically preserves the ordinal nature but is also more accurate than existing DML models.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Deep metric learning (DML) aims to automatically construct task-specific
distances or similarities of data, resulting in a low-dimensional
representation. Several significant metric-learning methods have been proposed.
Nonetheless, no approach guarantees the preservation of the ordinal nature of
the original data in a low-dimensional space. Ordinal data are ubiquitous in
real-world problems, such as the severity of symptoms in biomedical cases,
production quality in manufacturing, rating level in businesses, and aging
level in face recognition. This study proposes a novel angular triangle
distance (ATD) and ordinal triplet network (OTD) to obtain an accurate and
meaningful embedding space representation for ordinal data. The ATD projects
the ordinal relation of data in the angular space, whereas the OTD learns its
ordinal projection. We also demonstrated that our new distance measure
satisfies the distance metric properties mathematically. The proposed method
was assessed using real-world data with an ordinal nature, such as biomedical,
facial, and hand-gestured images. Extensive experiments have been conducted,
and the results show that our proposed method not only semantically preserves
the ordinal nature but is also more accurate than existing DML models.
Moreover, we also demonstrate that our proposed method outperforms the
state-of-the-art ordinal metric learning method.
Related papers
- UniDepth: Universal Monocular Metric Depth Estimation [81.80512457953903]
We propose a new model, UniDepth, capable of reconstructing metric 3D scenes from solely single images across domains.
Our model exploits a pseudo-spherical output representation, which disentangles camera and depth representations.
Thorough evaluations on ten datasets in a zero-shot regime consistently demonstrate the superior performance of UniDepth.
arXiv Detail & Related papers (2024-03-27T18:06:31Z) - Boundary Constraint-free Biomechanical Model-Based Surface Matching for Intraoperative Liver Deformation Correction [0.6249768559720122]
In image-guided liver surgery, 3D-3D non-rigid registration methods play a crucial role in estimating the mapping between the preoperative model and the intraoperative surface represented as point clouds.
This paper introduces a novel 3D-3D non-rigid registration method.
In contrast to the preceding techniques, our method uniquely incorporates the FEM within the surface matching term itself.
arXiv Detail & Related papers (2024-03-15T02:05:20Z) - Volumetric Semantically Consistent 3D Panoptic Mapping [77.13446499924977]
We introduce an online 2D-to-3D semantic instance mapping algorithm aimed at generating semantic 3D maps suitable for autonomous agents in unstructured environments.
It introduces novel ways of integrating semantic prediction confidence during mapping, producing semantic and instance-consistent 3D regions.
The proposed method achieves accuracy superior to the state of the art on public large-scale datasets, improving on a number of widely used metrics.
arXiv Detail & Related papers (2023-09-26T08:03:10Z) - Intrinsic dimension estimation for discrete metrics [65.5438227932088]
In this letter we introduce an algorithm to infer the intrinsic dimension (ID) of datasets embedded in discrete spaces.
We demonstrate its accuracy on benchmark datasets, and we apply it to analyze a metagenomic dataset for species fingerprinting.
This suggests that evolutive pressure acts on a low-dimensional manifold despite the high-dimensionality of sequences' space.
arXiv Detail & Related papers (2022-07-20T06:38:36Z) - BiometryNet: Landmark-based Fetal Biometry Estimation from Standard
Ultrasound Planes [9.919499846996269]
This paper describes BiometryNet, an end-to-end landmark regression framework for fetal biometry estimation.
It includes a novel Dynamic Orientation Determination (DOD) method for enforcing measurement-specific orientation consistency during network training.
To validate our method, we assembled a dataset of 3,398 ultrasound images from 1,829 subjects acquired in three clinical sites with seven different ultrasound devices.
arXiv Detail & Related papers (2022-06-29T14:32:32Z) - Unsupervised Domain Adaptation for Monocular 3D Object Detection via
Self-Training [57.25828870799331]
We propose STMono3D, a new self-teaching framework for unsupervised domain adaptation on Mono3D.
We develop a teacher-student paradigm to generate adaptive pseudo labels on the target domain.
STMono3D achieves remarkable performance on all evaluated datasets and even surpasses fully supervised results on the KITTI 3D object detection dataset.
arXiv Detail & Related papers (2022-04-25T12:23:07Z) - Geometry-Contrastive Transformer for Generalized 3D Pose Transfer [95.56457218144983]
The intuition of this work is to perceive the geometric inconsistency between the given meshes with the powerful self-attention mechanism.
We propose a novel geometry-contrastive Transformer that has an efficient 3D structured perceiving ability to the global geometric inconsistencies.
We present a latent isometric regularization module together with a novel semi-synthesized dataset for the cross-dataset 3D pose transfer task.
arXiv Detail & Related papers (2021-12-14T13:14:24Z) - Transductive Few-Shot Classification on the Oblique Manifold [5.115651633703363]
Few-shot learning attempts to learn with limited data.
In this work, we perform the feature extraction in the Euclidean space.
We also propose a non-parametric Region Self-attention with Spatial Pyramid Pooling.
arXiv Detail & Related papers (2021-08-09T13:01:03Z) - Deep Dimension Reduction for Supervised Representation Learning [51.10448064423656]
We propose a deep dimension reduction approach to learning representations with essential characteristics.
The proposed approach is a nonparametric generalization of the sufficient dimension reduction method.
We show that the estimated deep nonparametric representation is consistent in the sense that its excess risk converges to zero.
arXiv Detail & Related papers (2020-06-10T14:47:43Z) - Learning Flat Latent Manifolds with VAEs [16.725880610265378]
We propose an extension to the framework of variational auto-encoders, where the Euclidean metric is a proxy for the similarity between data points.
We replace the compact prior typically used in variational auto-encoders with a recently presented, more expressive hierarchical one.
We evaluate our method on a range of data-sets, including a video-tracking benchmark.
arXiv Detail & Related papers (2020-02-12T09:54:52Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.